【X先生】深度解析Python相关的10个岗位详细信息，一文读懂你到底该学些什么必要技能？(二)

# 1.矩形树图可视化学历要求
from pyecharts import TreeMap
education_table = {}
for x in education:
    education_table[x] = education.count(x)
key = []
values = []
for k,v in education_table.items():
    key.append(k)
    values.append(v)
data = []
for i in range(len(key)) :
    dict_01 = {"value": 40, "name": "我是A"}
    dict_01["value"] = values[i]
    dict_01["name"] = key[i]
    data.append(dict_01)
tree_map = TreeMap("矩形树图", width=1200, height=600)
tree_map.add("学历要求",data, is_label_show=True, label_pos='inside')

# 2.玫瑰饼图可视化薪资
import re
import math
'''
# 薪水分类
parameter : str_01--字符串原格式:20k-30k
returned value : (a0+b0)/2 --- 解析后变成数字求中间值：25.0
'''
def assort_salary(str_01):
    reg_str01 = "(\d+)"
    res_01 = re.findall(reg_str01, str_01)
    if len(res_01) == 2:
        a0 = int(res_01[0])
        b0 = int(res_01[1])
    else :
        a0 = int(res_01[0])
        b0 = int(res_01[0])
    return (a0+b0)/2
from pyecharts import Pie
salary_table = {}
for x in salary:
    salary_table[x] = salary.count(x)
key = ['5k以下','5k-10k','10k-20k','20k-30k','30k-40k','40k以上']
a0,b0,c0,d0,e0,f0=[0,0,0,0,0,0]
for k,v in salary_table.items():
    ave_salary = math.ceil(assort_salary(k))
    print(ave_salary)
    if ave_salary < 5:
        a0 = a0 + v
    elif ave_salary in range(5,10):
        b0 = b0 +v
    elif ave_salary in range(10,20):
        c0 = c0 +v
    elif ave_salary in range(20,30):
        d0 = d0 +v
    elif ave_salary in range(30,40):
        e0 = e0 +v
    else :
        f0 = f0 + v
values = [a0,b0,c0,d0,e0,f0]
pie = Pie("薪资玫瑰图", title_pos='center', width=900)
pie.add("salary",key,values,center=[40, 50],is_random=True,radius=[30, 75],rosetype="area",is_legend_show=False,is_label_show=True)

# 3.工作经验要求柱状图可视化
from pyecharts import Bar
workYear_table = {}
for x in workYear:
    workYear_table[x] = workYear.count(x)
key = []
values = []
for k,v in workYear_table.items():
    key.append(k)
    values.append(v)
bar = Bar("柱状图")
bar.add("workYear", key, values, is_stack=True,center= (40,60))

import jieba
from pyecharts import WordCloud
import pandas as pd
import re,numpy
stopwords_path = 'H:\PyCoding\Lagou_analysis\stopwords.txt'
def read_txt():
    with open("G:\lagou\Content\\ywkf_requirement.txt",encoding='gbk') as file:
        text = file.read()
        content = text
        # 去除所有评论里多余的字符
        content = re.sub('[,，。. \r\n]', '', content)
        segment = jieba.lcut(content)
        words_df = pd.DataFrame({'segment': segment})
        # quoting=3 表示stopwords.txt里的内容全部不引用
        stopwords = pd.read_csv(stopwords_path, index_col=False,quoting=3, sep="\t", names=['stopword'], encoding='utf-8')
        words_df = words_df[~words_df.segment.isin(stopwords.stopword)]
        words_stat = words_df.groupby(by=['segment'])['segment'].agg({"计数": numpy.size})
        words_stat = words_stat.reset_index().sort_values(by=["计数"], ascending=False)
        test = words_stat.head(200).values
        codes = [test[i][0] for i in range(0, len(test))]
        counts = [test[i][1] for i in range(0, len(test))]
        wordcloud = WordCloud(width=1300, height=620)
        wordcloud.add("必须技能", codes, counts, word_size_range=[20, 100])
        wordcloud.render("H:\PyCoding\Lagou_analysis\cloud_pit\ywkf_bxjn.html")